sentence-luke-japanese-base-lite

4.2K
14
1 language
license:apache-2.0
by
sonoisa
Embedding Model
OTHER
New
4K downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
Unknown
Mobile
Laptop
Server
Quick Summary

日本語Sentence-BERTモデルと同一のデータセットと設定で学習しました。 手元の非公開データセットでは、日本語Sentence-BERTモデルと比べて定量的な精度が同等〜0.

Code Examples

使い方pythontransformers
from transformers import MLukeTokenizer, LukeModel
import torch


class SentenceLukeJapanese:
    def __init__(self, model_name_or_path, device=None):
        self.tokenizer = MLukeTokenizer.from_pretrained(model_name_or_path)
        self.model = LukeModel.from_pretrained(model_name_or_path)
        self.model.eval()

        if device is None:
            device = "cuda" if torch.cuda.is_available() else "cpu"
        self.device = torch.device(device)
        self.model.to(device)

    def _mean_pooling(self, model_output, attention_mask):
        token_embeddings = model_output[0] #First element of model_output contains all token embeddings
        input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
        return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

    @torch.no_grad()
    def encode(self, sentences, batch_size=8):
        all_embeddings = []
        iterator = range(0, len(sentences), batch_size)
        for batch_idx in iterator:
            batch = sentences[batch_idx:batch_idx + batch_size]

            encoded_input = self.tokenizer.batch_encode_plus(batch, padding="longest", 
                                           truncation=True, return_tensors="pt").to(self.device)
            model_output = self.model(**encoded_input)
            sentence_embeddings = self._mean_pooling(model_output, encoded_input["attention_mask"]).to('cpu')

            all_embeddings.extend(sentence_embeddings)

        return torch.stack(all_embeddings)


MODEL_NAME = "sonoisa/sentence-luke-japanese-base-lite"
model = SentenceLukeJapanese(MODEL_NAME)

sentences = ["暴走したAI", "暴走した人工知能"]
sentence_embeddings = model.encode(sentences, batch_size=8)

print("Sentence embeddings:", sentence_embeddings)
使い方pythontransformers
from transformers import MLukeTokenizer, LukeModel
import torch


class SentenceLukeJapanese:
    def __init__(self, model_name_or_path, device=None):
        self.tokenizer = MLukeTokenizer.from_pretrained(model_name_or_path)
        self.model = LukeModel.from_pretrained(model_name_or_path)
        self.model.eval()

        if device is None:
            device = "cuda" if torch.cuda.is_available() else "cpu"
        self.device = torch.device(device)
        self.model.to(device)

    def _mean_pooling(self, model_output, attention_mask):
        token_embeddings = model_output[0] #First element of model_output contains all token embeddings
        input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
        return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

    @torch.no_grad()
    def encode(self, sentences, batch_size=8):
        all_embeddings = []
        iterator = range(0, len(sentences), batch_size)
        for batch_idx in iterator:
            batch = sentences[batch_idx:batch_idx + batch_size]

            encoded_input = self.tokenizer.batch_encode_plus(batch, padding="longest", 
                                           truncation=True, return_tensors="pt").to(self.device)
            model_output = self.model(**encoded_input)
            sentence_embeddings = self._mean_pooling(model_output, encoded_input["attention_mask"]).to('cpu')

            all_embeddings.extend(sentence_embeddings)

        return torch.stack(all_embeddings)


MODEL_NAME = "sonoisa/sentence-luke-japanese-base-lite"
model = SentenceLukeJapanese(MODEL_NAME)

sentences = ["暴走したAI", "暴走した人工知能"]
sentence_embeddings = model.encode(sentences, batch_size=8)

print("Sentence embeddings:", sentence_embeddings)
使い方pythontransformers
from transformers import MLukeTokenizer, LukeModel
import torch


class SentenceLukeJapanese:
    def __init__(self, model_name_or_path, device=None):
        self.tokenizer = MLukeTokenizer.from_pretrained(model_name_or_path)
        self.model = LukeModel.from_pretrained(model_name_or_path)
        self.model.eval()

        if device is None:
            device = "cuda" if torch.cuda.is_available() else "cpu"
        self.device = torch.device(device)
        self.model.to(device)

    def _mean_pooling(self, model_output, attention_mask):
        token_embeddings = model_output[0] #First element of model_output contains all token embeddings
        input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
        return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

    @torch.no_grad()
    def encode(self, sentences, batch_size=8):
        all_embeddings = []
        iterator = range(0, len(sentences), batch_size)
        for batch_idx in iterator:
            batch = sentences[batch_idx:batch_idx + batch_size]

            encoded_input = self.tokenizer.batch_encode_plus(batch, padding="longest", 
                                           truncation=True, return_tensors="pt").to(self.device)
            model_output = self.model(**encoded_input)
            sentence_embeddings = self._mean_pooling(model_output, encoded_input["attention_mask"]).to('cpu')

            all_embeddings.extend(sentence_embeddings)

        return torch.stack(all_embeddings)


MODEL_NAME = "sonoisa/sentence-luke-japanese-base-lite"
model = SentenceLukeJapanese(MODEL_NAME)

sentences = ["暴走したAI", "暴走した人工知能"]
sentence_embeddings = model.encode(sentences, batch_size=8)

print("Sentence embeddings:", sentence_embeddings)
使い方pythontransformers
from transformers import MLukeTokenizer, LukeModel
import torch


class SentenceLukeJapanese:
    def __init__(self, model_name_or_path, device=None):
        self.tokenizer = MLukeTokenizer.from_pretrained(model_name_or_path)
        self.model = LukeModel.from_pretrained(model_name_or_path)
        self.model.eval()

        if device is None:
            device = "cuda" if torch.cuda.is_available() else "cpu"
        self.device = torch.device(device)
        self.model.to(device)

    def _mean_pooling(self, model_output, attention_mask):
        token_embeddings = model_output[0] #First element of model_output contains all token embeddings
        input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
        return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

    @torch.no_grad()
    def encode(self, sentences, batch_size=8):
        all_embeddings = []
        iterator = range(0, len(sentences), batch_size)
        for batch_idx in iterator:
            batch = sentences[batch_idx:batch_idx + batch_size]

            encoded_input = self.tokenizer.batch_encode_plus(batch, padding="longest", 
                                           truncation=True, return_tensors="pt").to(self.device)
            model_output = self.model(**encoded_input)
            sentence_embeddings = self._mean_pooling(model_output, encoded_input["attention_mask"]).to('cpu')

            all_embeddings.extend(sentence_embeddings)

        return torch.stack(all_embeddings)


MODEL_NAME = "sonoisa/sentence-luke-japanese-base-lite"
model = SentenceLukeJapanese(MODEL_NAME)

sentences = ["暴走したAI", "暴走した人工知能"]
sentence_embeddings = model.encode(sentences, batch_size=8)

print("Sentence embeddings:", sentence_embeddings)
使い方pythontransformers
from transformers import MLukeTokenizer, LukeModel
import torch


class SentenceLukeJapanese:
    def __init__(self, model_name_or_path, device=None):
        self.tokenizer = MLukeTokenizer.from_pretrained(model_name_or_path)
        self.model = LukeModel.from_pretrained(model_name_or_path)
        self.model.eval()

        if device is None:
            device = "cuda" if torch.cuda.is_available() else "cpu"
        self.device = torch.device(device)
        self.model.to(device)

    def _mean_pooling(self, model_output, attention_mask):
        token_embeddings = model_output[0] #First element of model_output contains all token embeddings
        input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
        return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

    @torch.no_grad()
    def encode(self, sentences, batch_size=8):
        all_embeddings = []
        iterator = range(0, len(sentences), batch_size)
        for batch_idx in iterator:
            batch = sentences[batch_idx:batch_idx + batch_size]

            encoded_input = self.tokenizer.batch_encode_plus(batch, padding="longest", 
                                           truncation=True, return_tensors="pt").to(self.device)
            model_output = self.model(**encoded_input)
            sentence_embeddings = self._mean_pooling(model_output, encoded_input["attention_mask"]).to('cpu')

            all_embeddings.extend(sentence_embeddings)

        return torch.stack(all_embeddings)


MODEL_NAME = "sonoisa/sentence-luke-japanese-base-lite"
model = SentenceLukeJapanese(MODEL_NAME)

sentences = ["暴走したAI", "暴走した人工知能"]
sentence_embeddings = model.encode(sentences, batch_size=8)

print("Sentence embeddings:", sentence_embeddings)
使い方pythontransformers
from transformers import MLukeTokenizer, LukeModel
import torch


class SentenceLukeJapanese:
    def __init__(self, model_name_or_path, device=None):
        self.tokenizer = MLukeTokenizer.from_pretrained(model_name_or_path)
        self.model = LukeModel.from_pretrained(model_name_or_path)
        self.model.eval()

        if device is None:
            device = "cuda" if torch.cuda.is_available() else "cpu"
        self.device = torch.device(device)
        self.model.to(device)

    def _mean_pooling(self, model_output, attention_mask):
        token_embeddings = model_output[0] #First element of model_output contains all token embeddings
        input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
        return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

    @torch.no_grad()
    def encode(self, sentences, batch_size=8):
        all_embeddings = []
        iterator = range(0, len(sentences), batch_size)
        for batch_idx in iterator:
            batch = sentences[batch_idx:batch_idx + batch_size]

            encoded_input = self.tokenizer.batch_encode_plus(batch, padding="longest", 
                                           truncation=True, return_tensors="pt").to(self.device)
            model_output = self.model(**encoded_input)
            sentence_embeddings = self._mean_pooling(model_output, encoded_input["attention_mask"]).to('cpu')

            all_embeddings.extend(sentence_embeddings)

        return torch.stack(all_embeddings)


MODEL_NAME = "sonoisa/sentence-luke-japanese-base-lite"
model = SentenceLukeJapanese(MODEL_NAME)

sentences = ["暴走したAI", "暴走した人工知能"]
sentence_embeddings = model.encode(sentences, batch_size=8)

print("Sentence embeddings:", sentence_embeddings)
使い方pythontransformers
from transformers import MLukeTokenizer, LukeModel
import torch


class SentenceLukeJapanese:
    def __init__(self, model_name_or_path, device=None):
        self.tokenizer = MLukeTokenizer.from_pretrained(model_name_or_path)
        self.model = LukeModel.from_pretrained(model_name_or_path)
        self.model.eval()

        if device is None:
            device = "cuda" if torch.cuda.is_available() else "cpu"
        self.device = torch.device(device)
        self.model.to(device)

    def _mean_pooling(self, model_output, attention_mask):
        token_embeddings = model_output[0] #First element of model_output contains all token embeddings
        input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
        return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

    @torch.no_grad()
    def encode(self, sentences, batch_size=8):
        all_embeddings = []
        iterator = range(0, len(sentences), batch_size)
        for batch_idx in iterator:
            batch = sentences[batch_idx:batch_idx + batch_size]

            encoded_input = self.tokenizer.batch_encode_plus(batch, padding="longest", 
                                           truncation=True, return_tensors="pt").to(self.device)
            model_output = self.model(**encoded_input)
            sentence_embeddings = self._mean_pooling(model_output, encoded_input["attention_mask"]).to('cpu')

            all_embeddings.extend(sentence_embeddings)

        return torch.stack(all_embeddings)


MODEL_NAME = "sonoisa/sentence-luke-japanese-base-lite"
model = SentenceLukeJapanese(MODEL_NAME)

sentences = ["暴走したAI", "暴走した人工知能"]
sentence_embeddings = model.encode(sentences, batch_size=8)

print("Sentence embeddings:", sentence_embeddings)
使い方pythontransformers
from transformers import MLukeTokenizer, LukeModel
import torch


class SentenceLukeJapanese:
    def __init__(self, model_name_or_path, device=None):
        self.tokenizer = MLukeTokenizer.from_pretrained(model_name_or_path)
        self.model = LukeModel.from_pretrained(model_name_or_path)
        self.model.eval()

        if device is None:
            device = "cuda" if torch.cuda.is_available() else "cpu"
        self.device = torch.device(device)
        self.model.to(device)

    def _mean_pooling(self, model_output, attention_mask):
        token_embeddings = model_output[0] #First element of model_output contains all token embeddings
        input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
        return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

    @torch.no_grad()
    def encode(self, sentences, batch_size=8):
        all_embeddings = []
        iterator = range(0, len(sentences), batch_size)
        for batch_idx in iterator:
            batch = sentences[batch_idx:batch_idx + batch_size]

            encoded_input = self.tokenizer.batch_encode_plus(batch, padding="longest", 
                                           truncation=True, return_tensors="pt").to(self.device)
            model_output = self.model(**encoded_input)
            sentence_embeddings = self._mean_pooling(model_output, encoded_input["attention_mask"]).to('cpu')

            all_embeddings.extend(sentence_embeddings)

        return torch.stack(all_embeddings)


MODEL_NAME = "sonoisa/sentence-luke-japanese-base-lite"
model = SentenceLukeJapanese(MODEL_NAME)

sentences = ["暴走したAI", "暴走した人工知能"]
sentence_embeddings = model.encode(sentences, batch_size=8)

print("Sentence embeddings:", sentence_embeddings)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.